AI safety researcher

Yang Xiang

Swinburne University of Technology

Google Scholar dblp ORCID Homepage

Last 12 months2 papers

Attacks 1

AI safety papers from the last year

On this site: 21 papers

June 2026

Beyond Her: Safety Dynamics in Role-play AI Companions
Jun 27arXiv ↗

May 2026

Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
May 23AttacksarXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.